This is an automated email from the ASF dual-hosted git repository.
gurwls223 pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new b0dfa291a57 [SPARK-41643][CONNECT][PYTHON][FOLLOWUP] Deduplicate
docstrings of `Column.over`
b0dfa291a57 is described below
commit b0dfa291a57a325fac94297557612f8876cf816d
Author: Ruifeng Zheng <[email protected]>
AuthorDate: Tue Dec 27 21:52:12 2022 +0900
[SPARK-41643][CONNECT][PYTHON][FOLLOWUP] Deduplicate docstrings of
`Column.over`
### What changes were proposed in this pull request?
Deduplicate docstrings of `Column.over`
### Why are the changes needed?
For easier maintenance
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
existing UT
Closes #39244 from zhengruifeng/connect_deduplicate_col_over.
Authored-by: Ruifeng Zheng <[email protected]>
Signed-off-by: Hyukjin Kwon <[email protected]>
---
python/pyspark/sql/column.py | 3 +++
python/pyspark/sql/connect/column.py | 33 ++-------------------------------
2 files changed, 5 insertions(+), 31 deletions(-)
diff --git a/python/pyspark/sql/column.py b/python/pyspark/sql/column.py
index 96b4333e604..3bc49ef8031 100644
--- a/python/pyspark/sql/column.py
+++ b/python/pyspark/sql/column.py
@@ -1242,6 +1242,9 @@ class Column:
.. versionadded:: 1.4.0
+ .. versionchanged:: 3.4.0
+ Support Spark Connect.
+
Parameters
----------
window : :class:`WindowSpec`
diff --git a/python/pyspark/sql/connect/column.py
b/python/pyspark/sql/connect/column.py
index c9bc434fec3..fffecaf42a2 100644
--- a/python/pyspark/sql/connect/column.py
+++ b/python/pyspark/sql/connect/column.py
@@ -301,37 +301,6 @@ class Column:
return "Column<'%s'>" % self._expr.__repr__()
def over(self, window: "WindowSpec") -> "Column":
- """
- Define a windowing column.
-
- .. versionadded:: 3.4.0
-
- Parameters
- ----------
- window : :class:`WindowSpec`
-
- Returns
- -------
- :class:`Column`
-
- Examples
- --------
- >>> from pyspark.sql import Window
- >>> window = Window.partitionBy("name").orderBy("age") \
- .rowsBetween(Window.unboundedPreceding, Window.currentRow)
- >>> from pyspark.sql.functions import rank, min
- >>> from pyspark.sql.functions import desc
- >>> df = spark.createDataFrame(
- ... [(2, "Alice"), (5, "Bob")], ["age", "name"])
- >>> df.withColumn("rank", rank().over(window)) \
- .withColumn("min",
min('age').over(window)).sort(desc("age")).show()
- +---+-----+----+---+
- |age| name|rank|min|
- +---+-----+----+---+
- | 5| Bob| 1| 5|
- | 2|Alice| 1| 2|
- +---+-----+----+---+
- """
from pyspark.sql.connect.window import WindowSpec
if not isinstance(window, WindowSpec):
@@ -341,6 +310,8 @@ class Column:
return Column(WindowExpression(windowFunction=self._expr,
windowSpec=window))
+ over.__doc__ = PySparkColumn.over.__doc__
+
def isin(self, *cols: Any) -> "Column":
from pyspark.sql.connect.functions import lit
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
